Triple

T21992017
Position Surface form Disambiguated ID Type / Status
Subject Annabel Banks E543112 entity
Predicate relative P37 FINISHED
Object Michael Banks NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Michael Banks | Statement: [Annabel Banks, relative, Michael Banks]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Banks
Context triple: [Annabel Banks, relative, Michael Banks]
  • A. Michael Banks chosen
    Michael Banks is a fictional character from the Mary Poppins stories, depicted as one of the Banks children who later appears as an adult father in the sequel film.
  • B. Matthew Banks
    Matthew Banks is a British politician who served as a Member of Parliament before being succeeded by John David Pugh.
  • C. Don Banks
    Don Banks was an Australian composer and jazz musician known for his modernist concert works and numerous film and television scores.
  • D. Marcus Banks
    Marcus Banks is a former American professional basketball player who played as a point guard in the NBA for several teams in the 2000s.
  • E. Mike Banks
    Mike Banks was a British mountaineer best known for leading the first successful ascent of the Himalayan peak Rakaposhi.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69e0c48136b081908831fa907cc02e18 completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f1270e951081908deda039b47ca84b completed April 28, 2026, 9:30 p.m.
Created at: April 16, 2026, 8:05 p.m.